Search

Glass Box Machine Learning is, in this study, a type of partially supervised data mining and prediction technique, like a neural network in which each weight or pattern of mutually relevant weights is now replaced by a meaningful "probabilistic knowledge element." We apply it to retrospective cohort studies using large numbers of structured medical records to help select candidate patients for future cohort studies and similar clinical trials. Here it is applied to aid analysis of approaches to aid Deep Learning, but the method lends itself well to direct computation of odds with "explainability" in study design that can complement "Black Box" Deep Learning. Cohort studies and clinical trials traditionally involved at least one 2 × 2 contingency table, but in the age of emerging personalized medicine and the use of machine learning to discover and incorporate further relevant factors, these tables can extend into many extra dimensions as a 2 × 2 x 2 × 2 x ….data structure by considering different conditional demographic and clinical factors of a patient or group, as well as variations in treatment. We consider this in terms of multiple 2 × 2 x 2 data substructures where each one is summarized by an appropriate measure of risk and success called DOR*. This is the diagnostic odds ratio DOR for a specified disease conditional on a favorable outcome divided by the corresponding DOR conditional on an unfavorable outcome. Bleeding peptic ulcer was chosen as a complex disease with many influencing factors, one that is still subject to controversy and that highlights the challenges of using Real World Data., Competing Interests: Declaration of competing interest Dr. O. K. Baek is in receipt of a grant from a grant (23ZS1100) by the Electronics and Telecommunications Research Institute (ETRI) for the South Korean government to advance core technology research for self-improving integrated artificial intelligence systems, for which purpose this reported research was a part of the study. Dr. Barry Robson is a collaborator via Ingine Inc. as a contractor to the above grant. He is a member of the Editorial Board of Computers in Biology and Medicine and Assistant Editor of its sister journal, Informatics in Medicine Unlocked., (Copyright © 2024 Elsevier Ltd. All rights reserved.)

Although there are several decision aids for the treatment of localized prostate cancer (PCa), there are limitations in the consistency and certainty of the information provided. We aimed to better understand the treatment decision process and develop a decision-predicting model considering oncologic, demographic, socioeconomic, and geographic factors. Men newly diagnosed with localized PCa between 2010 and 2015 from the Surveillance, Epidemiology, and End Results Prostate with Watchful Waiting database were included (n = 255,837). We designed two prediction models: (1) Active surveillance/watchful waiting (AS/WW), radical prostatectomy (RP), and radiation therapy (RT) decision prediction in the entire cohort. (2) Prediction of AS/WW decisions in the low-risk cohort. The discrimination of the model was evaluated using the multiclass area under the curve (AUC). A plausible Shapley additive explanations value was used to explain the model's prediction results. Oncological variables affected the RP decisions most, whereas RT was highly affected by geographic factors. The dependence plot depicted the feature interactions in reaching a treatment decision. The decision predicting model achieved an overall multiclass AUC of 0.77, whereas 0.74 was confirmed for the low-risk model. Using a large population-based real-world database, we unraveled the complex decision-making process and visualized nonlinear feature interactions in localized PCa., (© 2023. The Author(s).)

Objective: There are difficulties on removing migrated disc herniation (MDH) using a microscope. The purpose of this study was to introduce a unilateral biportal endoscopic (UBE) translaminar approach to treat up-migrated lumbar disc herniation (LDH)., Patients and Methods: A total of 12 patients from March 2021 to February 2022 with up-migrated LDH were treated with a UBE translaminar approach. Clinical outcomes such as a visual analog scale (VAS) (back and leg pain) and MacNab criteria were assessed preoperative, postoperative, and 1 month after surgery., Results: Seven patients were diagnosed with high-grade up-migrated LDH, while five patients presented very-high grade up-migrated LDH. In all cases, the migrated LDH were removed completely and were confirmed by postoperative magnetic resonance imaging. The VAS for back pain were improved from 4.5 (SD = 3.1) to 2.0 (SD = 1.0) and 1.0 (SD = 1.0) for immediately postoperative and in 1-month follow-up, respectively, showing a statistically significant difference (p < 0.001). VAS for leg pain was 6.5 (SD = 2.5) preoperatively to 2.3 (SD = 1.1) and 0.8 (SD = 0.4) immediately postoperative and 1-month follow-up, respectively, also showing a significant difference (p < 0.001). According to the MacNab criteria, we observed excellent outcomes in 66.6% and good outcomes in 33.3%., Conclusion: The UBE translaminar approach showed a high success rate with high patient satisfaction for the management of up-migrated LDH. It could be considered a feasible alternative surgical option to treat up-migrated LDH., (© 2022 Asia Endosurgery Task Force and Japan Society of Endoscopic Surgery and John Wiley & Sons Australia, Ltd.)

Background: Kümmell disease has been treated with multiple surgical approaches, as described in the literature. However, there are few reports describing the technique of transpedicular intrabody cage insertion to enhance bony fusion and maintain the height of the vertebral body. We describe the technique of transpedicular intrabody cage insertion with posterolateral fusion in patients with Kümmell disease., Case Descriptions: Two patients diagnosed as having Kümmell disease were treated with transpedicular intrabody cage insertion with allogenic bone graft and posterolateral fusion with pedicle screw insertion. Both patients were followed up routinely at 1 month, 3 months, and 6 months, and clinical evaluations and radiography were performed. Patients 1 and 2 visited our center 8 months and 33 months, respectively. After surgery, we obtained additional radiography and magnetic resonance imaging. Postoperative computed tomography was performed at 3 months. The visual analog scale score for pain and the Cobb angle were evaluated preoperatively and postoperatively. The operation was completed in both patients without any complications. Immediate postoperative radiographs showed the intrabody cage with corrected kyphosis. Postoperative computed tomography scans at 3 months and radiographs and magnetic resonance imaging at 8 months (patient 1) and 33 months (patient 2) showed bone formation of the vertebral body involved with Kümmell disease and maintenance of the vertebral body height in both patients. Back pain was significantly improved in both patients., Conclusion: Transpedicular intrabody cage insertion is a safe and effective procedure for treating vertebral osteonecrosis to achieve bone formation at the site of vertebral osteonecrosis and to maintain body height., (Copyright © 2018 Elsevier Inc. All rights reserved.)

Study Design: Retrospective clinical study., Objective: To evaluate the effect of the limitation of flexion rotation clinically and radiologically after interspinous soft stabilization using a tension band system in grade 1 degenerative spondylolisthesis., Summary of Background Data: Although several studies have been published on the clinical effects of limiting rotatory motion using tension band systems, which mainly targets the limitation of flexion rather than that of extension, they were confined to the category of pedicle screw-based systems, revealing inconsistent long-term outcomes., Methods: Sixty-one patients with a mean age of 60.6 years (range, 28-76 yr) who underwent interspinous soft stabilization after decompression for grade 1 degenerative spondylolisthesis with stenosis between 2002 and 2004 were analyzed. At follow-up, the patients were divided into 2 groups on the basis of their achievement or failure to achieve flexion limitation. The clinical and radiological findings were analyzed. A multiple linear regression analysis was performed to determine the prognostic factors for surgical outcomes., Results: At a mean follow-up duration of 72.5 months (range, 61-82 mo), 51 patients were classified into the flexion-limited group and 10 into the flexion-unlimited group. Statistically significant improvements were noted only in the flexion-limited group in all clinical scores. In the flexion-unlimited group, there were significant deteriorations in flexion angle (P = 0.009), axial thickness of the ligamentum flavum (P = 0.013), and the foraminal cross-sectional area (P = 0.011), resulting in significant intergroup differences. The preoperative extension angle was identified as the most influential variable for the flexion limitation and the clinical outcomes., Conclusion: The effects of the limitation of flexion rotation achieved through interspinous soft stabilization using a tension band system after decompression were related to the prevention of late recurrent stenosis and resultant radicular pain caused by flexion instability. The extension potential at the index level was recognized as a major prognostic factor that can predict the flexion limitation and the clinical results., Level of Evidence: 4.

Objective: Dural sac cross-sectional area (DSCSA) is a way to measure the degree of central spinal canal compression. The objective was to investigate the correlation between the expansion ratio of DSCSA after unilateral laminotomy for bilateral decompression (ULBD) and the clinical results for lumbar spinal stenosis., Methods: We retrospectively reviewed the clinical data and radiographs of 103 patients who underwent ULBD for symptomatic spinal stenosis in one year. We compared preoperative and postoperative clinical data and DSCSA and evaluated the correlation between clinical and radiographic measurements., Results: There was a significant increase of DSCSA after ULBD (p=0.000) and mean expansion ratio of DSCSA was 203.7±147.2%(range -32.9-826.1%). Clinical outcomes, measured by VAS and ODI were improved significantly not only in early postoperative period, but also in the last follow-up. However, there were no statistically significant correlations between the preoperative DSCSA and clinical symptoms, Perioperative expansion ratio of DSCSA and clinical parameters were also not correlated to the improvement of clinical symptoms significantly in both early postoperative phase and last follow-up., Conclusion: Our result indicates that the DSCSA itself has a definite limitation to be correlated to the clinical symptoms, and thus meticulous correlation between the clinical presentation and MRI imaging is essential in determination of surgical treatment.